An interventional study of Controlled hypoglycaemic state while driving with a driving simulator in Diabetes and Diabetes Mellitus, Type 1, sponsored by Insel Gruppe AG, University Hospital Bern. Completed at 1 site in Switzerland. Open to participants aged 21 Years to 60 Years. Per ClinicalTrials.gov, last updated 2022-05-05.
Sponsored by Insel Gruppe AG, University Hospital Bern · Not applicable, Interventional, and Other
To analyse driving behavior of individuals with type 1 diabetes in eu- and mild hypoglycaemia using a validated research driving simulator. Based on the driving variables provided by the simulator the investigators aim at establishing algorithms capable of discriminating eu- and hypoglycemic driving patterns using machine learning classifiers.
Hypoglycaemia is among the most relevant acute complications of diabetes mellitus. During hypoglycaemia physical, psychomotor, executive and cognitive function significantly deteriorate. These are important prerequisites for safe driving. Accordingly, hypoglycaemia has consistently been shown to be associated with an increased risk of driving accidents and is, therefore, regarded as one of the relevant factors in traffic safety. Therefore, this study aims at evaluating a machine-learning based approach using in-vehicle data to detect hypoglycemia during driving at an early stage.
During controlled eu- and hypoglycemia, participants with type 1 diabetes mellitus drive in a validated driving simulator while in-vehicle data are recorded. Based on this data, the investigators aim at building machine learning classifiers to detect hypoglycemia during driving.
10,925 studies on the registry are indexed under Diabetes Mellitus; 1,318 are open to participants now.
This study's enrollment of 11 is below the median of 80 across 8,367 interventional studies indexed under Diabetes Mellitus.
Browse Diabetes Mellitus studies →Insel Gruppe AG, University Hospital Bern is the lead sponsor of 724 studies on the registry; 177 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Exclusion Criteria:
Other: Controlled hypoglycaemic state while driving with a driving simulator
Participants arrive in the morning after an overnight fast. During the controlled hypoglycaemic state, participants drive on a designated circuit using a driving simulator. Initially, a euglycaemic state (5.0-8.0 mmol/L) is kept stable and blood glucose is then progressively declined targeting at a level between 3.0-3.5 mmol/L by administering insulin. Blood glucose is kept stable in the hypoglycaemic range for 30 minutes. Thereafter, blood glucose is raised again and kept stable for another 30 minutes at an euglycaemic level between 5.0-8.0mmol/L. During the procedure, the investigators analyse counterregulatory hormones. Heart rate, skin conductance, CGM values, eye movement and facial expression are recorded by a smart-watch, a CGM device, an eye-tracker and an onboard camera, respectively. Participants are blinded to the blood glucose values during the procedure and have to rate their symptoms and their driving performance on a 0-6 scale every 15 minutes.
Diagnostic accuracy of the hypoglycemia warning system using in-vehicle data to detect hypoglycemia (blood glucose <3.9mmol/L) quantified as the area under the receiver operator characteristics curve (AUC ROC).
The machine learning model is developed and evaluated based on in-vehicle data generated in eu- and hypoglycemia. Detection performance of hypoglycemia is quantified as AUROC.
Time frame: 240 minutes
Diagnostic accuracy of the hypoglycemia warning system using wearable data to detect hypoglycemia (blood glucose <3.9mmol/L) quantified as the area under the receiver operator characteristics curve (AUC ROC).
The machine learning model is developed and evaluated based on wearable data recorded in eu- and hypoglycemia. Detection performance of hypoglycemia is quantified as AUROC.
Time frame: 240 minutes
Diagnostic accuracy of the hypoglycemia warning system using in-vehicle data and recordings of the continous glucose monitoring (CGM) system to detect hypoglycemia (blood glucose <3.9mmol/L) quantified as sensitivity and specificity.
The CGM device is in use during controlled eu- and hypoglycemia. Detection performance of hypoglycemia is quantified as sensitivity and specificity.
Time frame: 240 minutes
Diagnostic accuracy of the hypoglycemia warning system using wearable data and recordings of the CGM system to detect hypoglycemia (blood glucose <3.9mmol/L) quantified as sensitivity and specificity.
The CGM device is in use during controlled eu- and hypoglycemia. Detection performance of hypoglycemia is quantified as sensitivity and specificity.
Time frame: 240 minutes
Change in driving features over the glycemic trajectory.
Driving signals are recorded using a driving simulator.
Time frame: 240 minutes
Change of gaze coordinates over the glycemic trajectory.
Gaze coordinates are recorded using an eye-tracker device.
Time frame: 240 minutes
Change of head pose over the glycemic trajectory.
Head pose (position/rotation) are recorded using an eye-tracker device.
Time frame: 240 minutes
Change of heart rate over the glycemic trajectory
Heart rate is recorded using a holter-ECG device and wearables.
Time frame: 240 minutes
Change of heart rate variability over the glycemic trajectory
Heart rate variability is recorded using a holter-ECG device and wearables.
Time frame: 240 minutes
Change of electrodermal activity over the glycemic trajectory
Electrodermal activity is recorded using wearables.
Time frame: 240 minutes
Hypoglycemic symptoms over the glycemic trajectory.
Hypoglycemic symptoms are rated using a validated questionnaire (minimum score = 0, maximum score = 48, a higher score means more symptoms)
Time frame: 240 minutes
Time course of the hormonal response over the glycemic trajectory
Epinephrine, norepinephrine, glucagon, cortisol and growth hormone are measured at pre-defined time points.
Time frame: Time Frame: 240 minutes
Self assessment of driving performance over the glycemic trajectory.
Participants rate their driving performance on a 7-point Lickert Scale (lower value means poorer driving performance).
Time frame: 240 minutes
CGM accuracy over the glycemic trajectory
CGM values will be recorded using a CGM sensor (Dexcom G6). Venous blood glucose is considered as the reference. Accuracy will be quantified using mean absolute relative difference (MARD) from the gold-standard and using the Clarke error grid.
Time frame: 240 minutes
Incidence of Adverse Events (AEs)
Adverse Events will be recorded at each study visit.
Time frame: 2 weeks, from screening to close out visit in each participant
Incidence of Serious Adverse Events (SAEs)
Serious Adverse Events will be recorded at each study visit.
Time frame: 2 weeks, from screening to close out visit in each participant
Emotional response to hypoglycemia warning system
Physiological response is measured using an electro-dermal activity sensor (skin conductance) and eye tracker (eye blinks). Self-reported emotional response is assessed with scales (e.g., valence, arousal, annoyance, sense of urgency).
Time frame: 240 minutes
Technology acceptance of the hypoglycemia warning system
Technology acceptance is measured with user experience questionnaires, such as the Unified Technology Acceptance and Use of Technology Questionnaire from Venkatesh et al. (2012) and free words associations.
Time frame: 240 minutes
Plan to share: Yes — Any requests for raw data will be reviewed by the HEADWIND scientific study board comprising the principal investigator (PI) and Co-PI as well as senior researchers leading the involved research groups at Inselspital Bern, ETH Zurich, and University of St. Gallen. Only applications for non-commercial use will be considered and should be sent to the PI (Prof. Ch. Stettler). Applications should outline the purpose for the raw-data transfer. Any data that can be shared will need approval from the HEADWIND scientific study board and a Material Transfer Agreement in place. All data shared will be de-identified.
Supporting information: Study protocol, Analytic code
No publications or documents are linked to this record.
This study is completed, as verified in May 2022. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Insel Gruppe AG, University Hospital Bern